Investigation of powered 2-wheeler accident involvement in urban arterials by considering real-time traffic and weather data

Theofilatos, Athanasios; Yannis, George

doi:10.1080/15389588.2016.1198871

Cited by 18 publications

(6 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Steep grades, standard deviation of speed, temperature, and snow were found to be the most influential variables for this type of facility. Other authors used real-time traffic data for crash and safety analysis in urban arterials and urban expressways (Shi et al 2016a(Shi et al , 2016bTheofilatos and Yannis 2016;Muromachi 2013a, 2013b). Shankar et al (1996) observed that road safety studies were historically limited to the localization of fatalities, even though the estimation of consequences in terms of SL (from PDO to fatalities) could help in understanding the benefits accruing from countermeasures.…”

Section: Introductionmentioning

confidence: 99%

Analysis of factors affecting the severity of crashes in urban road intersections

Mussone

Bassani

Masci

2017

Accident Analysis & Prevention

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Analysis of factors affecting the severity of crashes in urban road intersections

Mussone

Bassani

Masci

2017

Accident Analysis & Prevention

View full text Add to dashboard Cite

“…In the former case, it is used to rank the variables according to their relative importance and thus assist in selecting the most appropriate independent variables before applying other statistical or ML models. This is a very common approach in road safety studies having a lot of candidate independent predictors ( 15 , 23 , 28 , 38 , 39 ).…”

Section: Methodsmentioning

confidence: 99%

“…Overall, some of the major factors that influence crash occurrence were found to be the variance of traffic parameters, such as coefficient of variation of speed and flow ( 4 , 9 , 15 , 19 ), as well as low visibility and adverse weather ( 20 – 22 ). Speed variance is also found to increase the probability of moped and motorcycle crashes ( 23 ), as well as rear-end crashes ( 24 ). Interestingly, low driving speeds were often found to be associated with increased crash risk ( 12 , 18 , 25 ).…”

Section: Introductionmentioning

confidence: 99%

Comparing Machine Learning and Deep Learning Methods for Real-Time Crash Prediction

Theofilatos

Chen

Antoniou

2019

Transportation Research Record

Self Cite

View full text Add to dashboard Cite

Although there are numerous studies examining the impact of real-time traffic and weather parameters on crash occurrence on freeways, to the best of the authors’ knowledge there are no studies which have compared the prediction performances of machine learning (ML) and deep learning (DL) models. The present study adds to current knowledge by comparing and validating ML and DL methods to predict real-time crash occurrence. To achieve this, real-time traffic and weather data from Attica Tollway in Greece were linked with historical crash data. The total data set was split into training/estimation (75%) and validation (25%) subsets, which were then standardized. First, the ML and DL prediction models were trained/estimated using the training data set. Afterwards, the models were compared on the basis of their performance metrics (accuracy, sensitivity, specificity, and area under curve, or AUC) on the test set. The models considered were k-nearest neighbor, Naïve Bayes, decision tree, random forest, support vector machine, shallow neural network, and, lastly, deep neural network. Overall, the DL model seems to be more appropriate, because it outperformed all other candidate models. More specifically, the DL model managed to achieve a balanced performance among all metrics compared with other models (total accuracy = 68.95%, sensitivity = 0.521, specificity = 0.77, AUC = 0.641). It is surprising though that the Naïve Bayes model achieved a good performance despite being far less complex than other models. The study findings are particularly useful, because they provide a first insight into performance of ML and DL models.

show abstract

“…Other factors, pointed out by researchers that influence the occurrence of accidents or accident severity include: low visibility and unfavorable weather [4,5]; Traffic flow and speed variations were found to influence powered two-wheeler (PTW) crashes [6]; Theofilatos et al (2012) [7] compared factors within and outside urban areas. Inside urban areas, factors such as young driver age, bicycles, intersections, and collisions with objects were found to affect accident severity; outside urban areas, weather, and head-on and side collisions affected accident severity.…”

Section: Literature Reviewmentioning

confidence: 99%

“…For future work, more recent data (2020/2021) will be provided to us that will allow us to improve the proposed work. Since we have highlighted motorcycles accidents as the main factor influencing accident severity it would be interesting to include traffic parameters and intensity to our approaches and compare the results to the results of Theofilatos et al (2016) [6], which has identified traffic flow and speed variations to influence powered two-wheeler (PTW) crashes. Additional machine learning algorithms and especially neural networks and deep learning approaches will also be applied as it has proven to be successful and sometimes outperforming simpler algorithms [14][15][16].…”

Section: Future Workmentioning

confidence: 99%

Machine Learning Approaches to Traffic Accident Analysis and Hotspot Prediction

et al. 2021

View full text Add to dashboard Cite

Traffic accidents are one of the most important concerns of the world, since they result in numerous casualties, injuries, and fatalities each year, as well as significant economic losses. There are many factors that are responsible for causing road accidents. If these factors can be better understood and predicted, it might be possible to take measures to mitigate the damages and its severity. The purpose of this work is to identify these factors using accident data from 2016 to 2019 from the district of Setúbal, Portugal. This work aims at developing models that can select a set of influential factors that may be used to classify the severity of an accident, supporting an analysis on the accident data. In addition, this study also proposes a predictive model for future road accidents based on past data. Various machine learning approaches are used to create these models. Supervised machine learning methods such as decision trees (DT), random forests (RF), logistic regression (LR), and naive Bayes (NB) are used, as well as unsupervised machine learning techniques including DBSCAN and hierarchical clustering. Results show that a rule-based model using the C5.0 algorithm is capable of accurately detecting the most relevant factors describing a road accident severity. Further, the results of the predictive model suggests the RF model could be a useful tool for forecasting accident hotspots.

show abstract

Investigation of powered 2-wheeler accident involvement in urban arterials by considering real-time traffic and weather data

Abstract: The findings of this study can contribute to the understanding of accident mechanisms of PTWs and reduce PTW accident risk in urban arterials.

Cited by 18 publications

References 40 publications

Analysis of factors affecting the severity of crashes in urban road intersections

Analysis of factors affecting the severity of crashes in urban road intersections

Comparing Machine Learning and Deep Learning Methods for Real-Time Crash Prediction

Machine Learning Approaches to Traffic Accident Analysis and Hotspot Prediction

Contact Info

Product

Resources

About